Table 4.
Summary of publications focused on Prostate histopathology image classification.
| Classifier | Reference | Year | AUC | Accuracy | Specificity | Sensitivity |
|---|---|---|---|---|---|---|
| KNN | [66] | 2003 | - | 0.917 | - | - |
| [18] | 2014 | - | 0.76 | - | - | |
| SVM | [48] | 2007 | - | 0.876 | - | - |
| [14] | 2013 | 0.75 | - | 0.83 | 0.81 | |
| [13] | 2019 | 0.98 ± 0.011 for artefacts versus glands 0.92 ± 0.04 for benign versus pathological |
0.95 ± 0.02 for artefacts versus glands 0.88 ± 0.07 for benign versus pathological |
0.95 ± 0.03 for artefacts versus glands 0.87 ± 0.07 for benign versus pathological |
0.94 ± 0.01 for artefacts versus glands 0.80 ± 0.06 for benign versus pathological |
|
| [58] | 2019 | - | 0.655 (one-shot classification) 0.92 (Binary classification) |
- | - | |
| Bag-of-Words | [22] | 2016 | - | 0.901 | 0.905 | 0.79 |
| MLA | [21] | 2018 | - | 0.883 | 0.94 | 0.876 |
| Boosting Cascade | [20] | 2006 | - | 0.88 | - | - |
| SVM and Random Forest | [19] | 2011 | 0.95 | - | 0.91 | 0.89 |
| Fuzzy Set Theory + Genetic Algorithm | [110] | 2013 | 0.824 | - | 0.95714 | 0.7097 |
| Adaboost | [2] | 2016 | - | 0.978 | - | - |